Training in progress, step 500
Browse files- model.safetensors +1 -1
- run-4/checkpoint-7000/config.json +26 -0
- run-4/checkpoint-7000/model.safetensors +3 -0
- run-4/checkpoint-7000/optimizer.pt +3 -0
- run-4/checkpoint-7000/rng_state.pth +3 -0
- run-4/checkpoint-7000/scheduler.pt +3 -0
- run-4/checkpoint-7000/special_tokens_map.json +7 -0
- run-4/checkpoint-7000/tokenizer.json +0 -0
- run-4/checkpoint-7000/tokenizer_config.json +55 -0
- run-4/checkpoint-7000/trainer_state.json +203 -0
- run-4/checkpoint-7000/training_args.bin +3 -0
- run-4/checkpoint-7000/vocab.txt +0 -0
- run-9/checkpoint-500/config.json +26 -0
- run-9/checkpoint-500/model.safetensors +3 -0
- run-9/checkpoint-500/optimizer.pt +3 -0
- run-9/checkpoint-500/rng_state.pth +3 -0
- run-9/checkpoint-500/scheduler.pt +3 -0
- run-9/checkpoint-500/special_tokens_map.json +7 -0
- run-9/checkpoint-500/tokenizer.json +0 -0
- run-9/checkpoint-500/tokenizer_config.json +55 -0
- run-9/checkpoint-500/trainer_state.json +31 -0
- run-9/checkpoint-500/training_args.bin +3 -0
- run-9/checkpoint-500/vocab.txt +0 -0
- training_args.bin +1 -1
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1340618660
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7c0863a06a044fb994213ba385bd258e01513c1d2e24cea07e3940a59e71830b
|
3 |
size 1340618660
|
run-4/checkpoint-7000/config.json
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "bert-large-uncased",
|
3 |
+
"architectures": [
|
4 |
+
"BertForMultipleChoice"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"gradient_checkpointing": false,
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_dropout_prob": 0.1,
|
11 |
+
"hidden_size": 1024,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 4096,
|
14 |
+
"layer_norm_eps": 1e-12,
|
15 |
+
"max_position_embeddings": 512,
|
16 |
+
"model_type": "bert",
|
17 |
+
"num_attention_heads": 16,
|
18 |
+
"num_hidden_layers": 24,
|
19 |
+
"pad_token_id": 0,
|
20 |
+
"position_embedding_type": "absolute",
|
21 |
+
"torch_dtype": "float32",
|
22 |
+
"transformers_version": "4.40.1",
|
23 |
+
"type_vocab_size": 2,
|
24 |
+
"use_cache": true,
|
25 |
+
"vocab_size": 30522
|
26 |
+
}
|
run-4/checkpoint-7000/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9fe60aafde78975bafec1a842cfbb18b4f2f52bd219b5c19b49f2d98482db34f
|
3 |
+
size 1340618660
|
run-4/checkpoint-7000/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:383d9a7b504625c1424693f0af20f92a86ae57a54be379c656f65f56e0c01ac9
|
3 |
+
size 2681472237
|
run-4/checkpoint-7000/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9e8822b3ce842a84ff93b4e9e34c5d6cc8389740adb793137e0de79524460bc4
|
3 |
+
size 14244
|
run-4/checkpoint-7000/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5cbbe4b99d578d719b8b98b39cc4c5e4a155347da6827e4d0ea2bb0db5ec29a8
|
3 |
+
size 1064
|
run-4/checkpoint-7000/special_tokens_map.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"mask_token": "[MASK]",
|
4 |
+
"pad_token": "[PAD]",
|
5 |
+
"sep_token": "[SEP]",
|
6 |
+
"unk_token": "[UNK]"
|
7 |
+
}
|
run-4/checkpoint-7000/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-4/checkpoint-7000/tokenizer_config.json
ADDED
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "[PAD]",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"100": {
|
12 |
+
"content": "[UNK]",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"101": {
|
20 |
+
"content": "[CLS]",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"102": {
|
28 |
+
"content": "[SEP]",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"103": {
|
36 |
+
"content": "[MASK]",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
}
|
43 |
+
},
|
44 |
+
"clean_up_tokenization_spaces": true,
|
45 |
+
"cls_token": "[CLS]",
|
46 |
+
"do_lower_case": true,
|
47 |
+
"mask_token": "[MASK]",
|
48 |
+
"model_max_length": 512,
|
49 |
+
"pad_token": "[PAD]",
|
50 |
+
"sep_token": "[SEP]",
|
51 |
+
"strip_accents": null,
|
52 |
+
"tokenize_chinese_chars": true,
|
53 |
+
"tokenizer_class": "BertTokenizer",
|
54 |
+
"unk_token": "[UNK]"
|
55 |
+
}
|
run-4/checkpoint-7000/trainer_state.json
ADDED
@@ -0,0 +1,203 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 9.383378016085791,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 7000,
|
7 |
+
"is_hyper_param_search": true,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.6702412868632708,
|
13 |
+
"grad_norm": 13.804513931274414,
|
14 |
+
"learning_rate": 1.2284160000241888e-05,
|
15 |
+
"loss": 0.5698,
|
16 |
+
"step": 500
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 1.0,
|
20 |
+
"eval_accuracy": 0.7532685399055481,
|
21 |
+
"eval_loss": 0.4876743257045746,
|
22 |
+
"eval_runtime": 9.5369,
|
23 |
+
"eval_samples_per_second": 312.785,
|
24 |
+
"eval_steps_per_second": 19.608,
|
25 |
+
"step": 746
|
26 |
+
},
|
27 |
+
{
|
28 |
+
"epoch": 1.3404825737265416,
|
29 |
+
"grad_norm": 23.23216438293457,
|
30 |
+
"learning_rate": 1.1401677241603822e-05,
|
31 |
+
"loss": 0.4247,
|
32 |
+
"step": 1000
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 2.0,
|
36 |
+
"eval_accuracy": 0.7777405381202698,
|
37 |
+
"eval_loss": 0.5234329700469971,
|
38 |
+
"eval_runtime": 9.4342,
|
39 |
+
"eval_samples_per_second": 316.19,
|
40 |
+
"eval_steps_per_second": 19.821,
|
41 |
+
"step": 1492
|
42 |
+
},
|
43 |
+
{
|
44 |
+
"epoch": 2.0107238605898123,
|
45 |
+
"grad_norm": 6.197817325592041,
|
46 |
+
"learning_rate": 1.0519194482965755e-05,
|
47 |
+
"loss": 0.3313,
|
48 |
+
"step": 1500
|
49 |
+
},
|
50 |
+
{
|
51 |
+
"epoch": 2.680965147453083,
|
52 |
+
"grad_norm": 20.681987762451172,
|
53 |
+
"learning_rate": 9.63671172432769e-06,
|
54 |
+
"loss": 0.1575,
|
55 |
+
"step": 2000
|
56 |
+
},
|
57 |
+
{
|
58 |
+
"epoch": 3.0,
|
59 |
+
"eval_accuracy": 0.7740529775619507,
|
60 |
+
"eval_loss": 0.6654106378555298,
|
61 |
+
"eval_runtime": 9.4207,
|
62 |
+
"eval_samples_per_second": 316.642,
|
63 |
+
"eval_steps_per_second": 19.85,
|
64 |
+
"step": 2238
|
65 |
+
},
|
66 |
+
{
|
67 |
+
"epoch": 3.351206434316354,
|
68 |
+
"grad_norm": 0.6577324271202087,
|
69 |
+
"learning_rate": 8.754228965689622e-06,
|
70 |
+
"loss": 0.1178,
|
71 |
+
"step": 2500
|
72 |
+
},
|
73 |
+
{
|
74 |
+
"epoch": 4.0,
|
75 |
+
"eval_accuracy": 0.7763996124267578,
|
76 |
+
"eval_loss": 1.094183087348938,
|
77 |
+
"eval_runtime": 9.4168,
|
78 |
+
"eval_samples_per_second": 316.775,
|
79 |
+
"eval_steps_per_second": 19.858,
|
80 |
+
"step": 2984
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 4.021447721179625,
|
84 |
+
"grad_norm": 5.022602558135986,
|
85 |
+
"learning_rate": 7.871746207051555e-06,
|
86 |
+
"loss": 0.0777,
|
87 |
+
"step": 3000
|
88 |
+
},
|
89 |
+
{
|
90 |
+
"epoch": 4.6916890080428955,
|
91 |
+
"grad_norm": 0.7826739549636841,
|
92 |
+
"learning_rate": 6.989263448413488e-06,
|
93 |
+
"loss": 0.044,
|
94 |
+
"step": 3500
|
95 |
+
},
|
96 |
+
{
|
97 |
+
"epoch": 5.0,
|
98 |
+
"eval_accuracy": 0.782433807849884,
|
99 |
+
"eval_loss": 1.2965056896209717,
|
100 |
+
"eval_runtime": 9.3869,
|
101 |
+
"eval_samples_per_second": 317.783,
|
102 |
+
"eval_steps_per_second": 19.921,
|
103 |
+
"step": 3730
|
104 |
+
},
|
105 |
+
{
|
106 |
+
"epoch": 5.361930294906166,
|
107 |
+
"grad_norm": 1.7349833250045776,
|
108 |
+
"learning_rate": 6.106780689775422e-06,
|
109 |
+
"loss": 0.0345,
|
110 |
+
"step": 4000
|
111 |
+
},
|
112 |
+
{
|
113 |
+
"epoch": 6.0,
|
114 |
+
"eval_accuracy": 0.7861213684082031,
|
115 |
+
"eval_loss": 1.1750046014785767,
|
116 |
+
"eval_runtime": 9.4116,
|
117 |
+
"eval_samples_per_second": 316.949,
|
118 |
+
"eval_steps_per_second": 19.869,
|
119 |
+
"step": 4476
|
120 |
+
},
|
121 |
+
{
|
122 |
+
"epoch": 6.032171581769437,
|
123 |
+
"grad_norm": 16.81600570678711,
|
124 |
+
"learning_rate": 5.224297931137354e-06,
|
125 |
+
"loss": 0.0227,
|
126 |
+
"step": 4500
|
127 |
+
},
|
128 |
+
{
|
129 |
+
"epoch": 6.702412868632708,
|
130 |
+
"grad_norm": 0.004451041109859943,
|
131 |
+
"learning_rate": 4.341815172499288e-06,
|
132 |
+
"loss": 0.0164,
|
133 |
+
"step": 5000
|
134 |
+
},
|
135 |
+
{
|
136 |
+
"epoch": 7.0,
|
137 |
+
"eval_accuracy": 0.7827690243721008,
|
138 |
+
"eval_loss": 1.4659219980239868,
|
139 |
+
"eval_runtime": 9.615,
|
140 |
+
"eval_samples_per_second": 310.243,
|
141 |
+
"eval_steps_per_second": 19.449,
|
142 |
+
"step": 5222
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 7.372654155495979,
|
146 |
+
"grad_norm": 4.934184551239014,
|
147 |
+
"learning_rate": 3.4593324138612214e-06,
|
148 |
+
"loss": 0.0136,
|
149 |
+
"step": 5500
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 8.0,
|
153 |
+
"eval_accuracy": 0.7847804427146912,
|
154 |
+
"eval_loss": 1.4372460842132568,
|
155 |
+
"eval_runtime": 9.4141,
|
156 |
+
"eval_samples_per_second": 316.864,
|
157 |
+
"eval_steps_per_second": 19.864,
|
158 |
+
"step": 5968
|
159 |
+
},
|
160 |
+
{
|
161 |
+
"epoch": 8.04289544235925,
|
162 |
+
"grad_norm": 6.715782642364502,
|
163 |
+
"learning_rate": 2.5768496552231545e-06,
|
164 |
+
"loss": 0.0143,
|
165 |
+
"step": 6000
|
166 |
+
},
|
167 |
+
{
|
168 |
+
"epoch": 8.71313672922252,
|
169 |
+
"grad_norm": 0.0020331561099737883,
|
170 |
+
"learning_rate": 1.694366896585088e-06,
|
171 |
+
"loss": 0.0059,
|
172 |
+
"step": 6500
|
173 |
+
},
|
174 |
+
{
|
175 |
+
"epoch": 9.0,
|
176 |
+
"eval_accuracy": 0.7871270775794983,
|
177 |
+
"eval_loss": 1.520074725151062,
|
178 |
+
"eval_runtime": 9.3955,
|
179 |
+
"eval_samples_per_second": 317.492,
|
180 |
+
"eval_steps_per_second": 19.903,
|
181 |
+
"step": 6714
|
182 |
+
},
|
183 |
+
{
|
184 |
+
"epoch": 9.383378016085791,
|
185 |
+
"grad_norm": 28.452878952026367,
|
186 |
+
"learning_rate": 8.118841379470213e-07,
|
187 |
+
"loss": 0.0081,
|
188 |
+
"step": 7000
|
189 |
+
}
|
190 |
+
],
|
191 |
+
"logging_steps": 500,
|
192 |
+
"max_steps": 7460,
|
193 |
+
"num_input_tokens_seen": 0,
|
194 |
+
"num_train_epochs": 10,
|
195 |
+
"save_steps": 500,
|
196 |
+
"total_flos": 1.8226917764893548e+16,
|
197 |
+
"train_batch_size": 16,
|
198 |
+
"trial_name": null,
|
199 |
+
"trial_params": {
|
200 |
+
"learning_rate": 1.3166642758879955e-05,
|
201 |
+
"per_device_train_batch_size": 16
|
202 |
+
}
|
203 |
+
}
|
run-4/checkpoint-7000/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:27b6f814d1d31383705935d6e962b569d93dc7baa4de5cb209ef031fca6730c2
|
3 |
+
size 5048
|
run-4/checkpoint-7000/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-9/checkpoint-500/config.json
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "bert-large-uncased",
|
3 |
+
"architectures": [
|
4 |
+
"BertForMultipleChoice"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"gradient_checkpointing": false,
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_dropout_prob": 0.1,
|
11 |
+
"hidden_size": 1024,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 4096,
|
14 |
+
"layer_norm_eps": 1e-12,
|
15 |
+
"max_position_embeddings": 512,
|
16 |
+
"model_type": "bert",
|
17 |
+
"num_attention_heads": 16,
|
18 |
+
"num_hidden_layers": 24,
|
19 |
+
"pad_token_id": 0,
|
20 |
+
"position_embedding_type": "absolute",
|
21 |
+
"torch_dtype": "float32",
|
22 |
+
"transformers_version": "4.40.1",
|
23 |
+
"type_vocab_size": 2,
|
24 |
+
"use_cache": true,
|
25 |
+
"vocab_size": 30522
|
26 |
+
}
|
run-9/checkpoint-500/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7c0863a06a044fb994213ba385bd258e01513c1d2e24cea07e3940a59e71830b
|
3 |
+
size 1340618660
|
run-9/checkpoint-500/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f585d77c612aa84e41faee08fa236a1e52226fe23b3c89455fa56c76d8bf5244
|
3 |
+
size 2681472237
|
run-9/checkpoint-500/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b0c317b20a8b0f126de354e22abe6285be95b0457be6843da518d21b802633c6
|
3 |
+
size 14244
|
run-9/checkpoint-500/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:40893a1b560d118c7a39b812ee803c02f5e42e174d72b1b399e9c4c49d0dbc05
|
3 |
+
size 1064
|
run-9/checkpoint-500/special_tokens_map.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"mask_token": "[MASK]",
|
4 |
+
"pad_token": "[PAD]",
|
5 |
+
"sep_token": "[SEP]",
|
6 |
+
"unk_token": "[UNK]"
|
7 |
+
}
|
run-9/checkpoint-500/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-9/checkpoint-500/tokenizer_config.json
ADDED
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "[PAD]",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"100": {
|
12 |
+
"content": "[UNK]",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"101": {
|
20 |
+
"content": "[CLS]",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"102": {
|
28 |
+
"content": "[SEP]",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"103": {
|
36 |
+
"content": "[MASK]",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
}
|
43 |
+
},
|
44 |
+
"clean_up_tokenization_spaces": true,
|
45 |
+
"cls_token": "[CLS]",
|
46 |
+
"do_lower_case": true,
|
47 |
+
"mask_token": "[MASK]",
|
48 |
+
"model_max_length": 512,
|
49 |
+
"pad_token": "[PAD]",
|
50 |
+
"sep_token": "[SEP]",
|
51 |
+
"strip_accents": null,
|
52 |
+
"tokenize_chinese_chars": true,
|
53 |
+
"tokenizer_class": "BertTokenizer",
|
54 |
+
"unk_token": "[UNK]"
|
55 |
+
}
|
run-9/checkpoint-500/trainer_state.json
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.6702412868632708,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 500,
|
7 |
+
"is_hyper_param_search": true,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.6702412868632708,
|
13 |
+
"grad_norm": 1.9480586051940918,
|
14 |
+
"learning_rate": 2.5188212161556512e-05,
|
15 |
+
"loss": 0.7022,
|
16 |
+
"step": 500
|
17 |
+
}
|
18 |
+
],
|
19 |
+
"logging_steps": 500,
|
20 |
+
"max_steps": 7460,
|
21 |
+
"num_input_tokens_seen": 0,
|
22 |
+
"num_train_epochs": 10,
|
23 |
+
"save_steps": 500,
|
24 |
+
"total_flos": 1.012015795464e+16,
|
25 |
+
"train_batch_size": 16,
|
26 |
+
"trial_name": null,
|
27 |
+
"trial_params": {
|
28 |
+
"learning_rate": 2.699771016166833e-05,
|
29 |
+
"per_device_train_batch_size": 16
|
30 |
+
}
|
31 |
+
}
|
run-9/checkpoint-500/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5f7b779a2fff70b87968b75f4b25894d79dc52b9c0b0dd4227ed1fb52a39031f
|
3 |
+
size 5048
|
run-9/checkpoint-500/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5048
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5f7b779a2fff70b87968b75f4b25894d79dc52b9c0b0dd4227ed1fb52a39031f
|
3 |
size 5048
|